COURSE UNIT TITLE COURSE UNIT CODE SEMESTER THEORY + PRACTICE (Hour) ECTS
IMAGE SENSORS & PROCESSING
STS613
-
3 + 0
10
TYPE OF COURSE UNIT Elective Course
LEVEL OF COURSE UNIT Doctorate Of Science
YEAR OF STUDY -
SEMESTER -
NUMBER OF ECTS CREDITS ALLOCATED 10
NAME OF LECTURER(S) -
LEARNING OUTCOMES OF THE COURSE UNIT
At the end of this course, the students; 1) Know the history and application areas of image processing. 2) Learn digital image models. 3) Learn spatial and gray level solutions. 4) 5) Learns and applies arithmetic and logic operations on images. 6) Learn and apply image enhancement and filtering methods.
MODE OF DELIVERY Face to face
PRE-REQUISITES OF THE COURSE No
RECOMMENDED OPTIONAL PROGRAMME COMPONENT none
COURSE DEFINITION Introduction to computer vision, image formation,Image model, image acquisition schemes,Lower-level vision problems: smoothing, edge detection, edge linking, multiscale approaches,Moderate vision problems: surface creation, drawing from tones, motion and stereo images,High-level vision problems: model-based vision, semantic networks, generalized cylinders,Hough transformation
COURSE CONTENTS WEEK TOPICS 1st Week Introduction to computer vision, image formation 2nd Week Introduction to computer vision, image formation 3rd Week Image model, image acquisition schemes 4th Week Image model, image acquisition schemes 5th Week Lower-level vision problems: smoothing, edge detection, edge linking, multiscale approaches 6th Week Lower-level vision problems: smoothing, edge detection, edge linking, multiscale approaches 7th Week Moderate vision problems: surface creation, drawing from tones, motion and stereo images 8th Week Midterm 9th Week Moderate vision problems: surface creation, drawing from tones, motion and stereo images 10th Week High-level vision problems: model-based vision, semantic networks, generalized cylinders 11th Week High-level vision problems: model-based vision, semantic networks, generalized cylinders 12th Week High-level vision problems: model-based vision, semantic networks, generalized cylinders 13th Week Hough transformation 14th Week Hough transformation
RECOMENDED OR REQUIRED READING Digital Image Processing, Rafael C. Gonzales and Richard E. Woods, Printice Hall, 2002.
PLANNED LEARNING ACTIVITIES AND TEACHING METHODS Presentation,Lecture,Report Preparation
ASSESSMENT METHODS AND CRITERIA Quantity Percentage(%) Mid-term 1 25 Assignment 1 25 Quiz 2 15 Attendance 1 5 Total(%) 70 Contribution of In-term Studies to Overall Grade(%) 70 Contribution of Final Examination to Overall Grade(%) 30 Total(%) 100
ECTS WORKLOAD
Activities
Number
Hours
Workload
Midterm exam 1 2 2 Preparation for Quiz 1 34 34 Individual or group work 14 8 112 Preparation for Final exam 1 60 60 Course hours 14 3 42 Preparation for Midterm exam 1 25 25 Laboratory (including preparation) Final exam 1 2 2 Homework 2 10 20 Quiz 2 2 4 Total Workload 301 Total Workload / 30 10,03 ECTS Credits of the Course 10
LANGUAGE OF INSTRUCTION Turkish
WORK PLACEMENT(S) No
KEY LEARNING OUTCOMES (KLO) / MATRIX OF LEARNING OUTCOMES (LO)
LO1 LO2 LO3 LO4 LO5 LO6 K1 K2 X X X X X X K3 X X X X X X K4 X X X X X K5 X X X X X K6 K7 K8 K9 K10 K11